Advancing Generalizable Remote Physiological Measurement through the Integration of Explicit and Implicit Prior Knowledge

TL;DR

This paper introduces a novel rPPG framework that integrates explicit and implicit prior knowledge to improve cross-dataset generalization in remote physiological measurement, outperforming existing methods.

Contribution

The study proposes a new method combining explicit prior knowledge with a two-branch network for noise disentanglement, enhancing cross-dataset generalization in rPPG tasks.

Findings

Outperforms state-of-the-art on RGB cross-dataset evaluation

Generalizes effectively from RGB to NIR datasets

Leverages prior knowledge to reduce noise impact

Abstract

Remote photoplethysmography (rPPG) is a promising technology that captures physiological signals from face videos, with potential applications in medical health, emotional computing, and biosecurity recognition. The demand for rPPG tasks has expanded from demonstrating good performance on intra-dataset testing to cross-dataset testing (i.e., domain generalization). However, most existing methods have overlooked the prior knowledge of rPPG, resulting in poor generalization ability. In this paper, we propose a novel framework that simultaneously utilizes explicit and implicit prior knowledge in the rPPG task. Specifically, we systematically analyze the causes of noise sources (e.g., different camera, lighting, skin types, and movement) across different domains and incorporate these prior knowledge into the network. Additionally, we leverage a two-branch network to disentangle the physiological feature distribution from noises through implicit label correlation. Our extensive experiments demonstrate that the proposed method not only outperforms state-of-the-art methods on RGB cross-dataset evaluation but also generalizes well from RGB datasets to NIR datasets. The code is available at https://github.com/keke-nice/Greip.